© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59500
    Prev
    Next
    INDEX
    Explanations

    information technology and processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soixante
    -0.83
     marbre
    -0.78
     bambou
    -0.78
     cinquante
    -0.77
    ファイル
    -0.77
     hundert
    -0.77
     Russel
    -0.73
    ringa
    -0.73
     estran
    -0.73
     développement
    -0.73
    POSITIVE LOGITS
     technology
    1.20
     processing
    1.13
    technology
    1.02
     systems
    0.97
    processing
    0.95
     system
    0.94
     hiding
    0.93
     handling
    0.91
     Technology
    0.89
     seeking
    0.88
    Activations Density 0.028%

    No Known Activations